Advances in machine learning are reshaping the foundations of science and technology. Despite their empirical success, a rigorous theoretical understanding of when and why machine learning algorithms succeed or fail remains limited. My research aims to bridge this gap by developing theoretical frameworks that explain the underlying mechanisms of machine learning and guide the design of principled and effective algorithms. In particular, I aim to understand the limitations of existing methods and to develop theoretically grounded solutions that address these limitations. My current research focuses on language models and representation learning.

Selected publications are listed below. For a full list, please see the Publications page.

Language Models

• How to Correctly Report LLM-as-a-Judge Evaluations
  ICML 2026

• Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
  ICML 2026

Representation Learning

• On the Similarities of Embeddings in Contrastive Learning
  ICML 2025

• A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
  AISTATS 2025

• Analysis of Using Sigmoid Loss for Contrastive Learning
  AISTATS 2024